AMABWIRIZA

BigScience na Moderi YUBURYO

BLOOM is a 176-billion-parameter multilingual language model produced by the BigScience collaboration and released with its research documentation.

Umva iki gitaboAI-byavuzwe · ~2 min

Kuriyi page2 min soma
  1. Incamake
  2. Kwibira cyane
  3. Gushyira mu bikorwa Isi
  4. Ejo hazaza ha BigScience na Moderi ya BLOOM
  5. Kubishyira mubikorwa
  6. Komeza Ubushakashatsi
  7. Ibibazo bikunze kubazwa

Incamake

Its ROOTS training corpus included natural and programming languages, making it a prominent open-access research model.

Kwibira cyane

The BigScience paper describes BLOOM as a decoder-only Transformer with 176 billion parameters. It was trained on ROOTS, a corpus assembled from hundreds of sources in 46 natural languages and 13 programming languages. The collaboration released the model and code under the Responsible AI License and documented data and training choices. Its open-access release supports research, but does not remove the need to consider the license, model limitations, or the represented language distribution.

Gushyira mu bikorwa Isi

Kubyara no kuzuza inyandiko mururimi rwinshi, harimo nizindi zidakwiye nubucuruzi bwubucuruzi

Gukora nkubushakashatsi bwibanze bwo kwiga kubogama, kwimura indimi nyinshi, hamwe nimyitwarire yo gupima

Kuringaniza neza mubikorwa byihariye cyangwa amabwiriza-akurikira nka BLOOMZ kumiryango itari icyongereza

Gutanga icyitegererezo cyuzuye kubanyeshuri biga amakuru yerekana amahugurwa hamwe nimpushya za AI

Ejo hazaza ha BigScience na Moderi ya BLOOM

BigScience yerekanye ko nini-nini, iyobowe na AI ku mugaragaro birashoboka, kandi icyitegererezo cyayo cyagize uruhare nyuma yo gusohora no kwaguka gukorera mu mucyo. Ibikorwa bizaza mu ndimi nyinshi birashoboka ko bizashingira kumasomo yayo mubyangombwa byamakuru no gukwirakwiza ururimi, mugihe icyitegererezo gishya, cyiza cyarenze BLOOM kubushobozi buke. Umurage wacyo urambye ni ihame ryo gutangaza amakarita yicyitegererezo, ibisobanuro byamakuru, hamwe nimpushya zibishinzwe, hiyongereyeho gihamya ko compte rusange ishobora guhugura imipaka yerekana imipaka.

Kubishyira mubikorwa

Impamvu ari ngombwa

  • Ingamba z'abacuruzi. Ibishushanyo mbonera byabacuruzi bigira ingaruka kubiranga ikipe yawe ishobora kubaka ubutaha.
  • Igiciro na bije. Amagambo yubucuruzi nuburyo bwo kohereza bigira ingaruka kubiciro byigihe kirekire ningaruka.
  • Ibyago n'umutekano. Isosiyete ishimangira gushiraho ibicuruzwa bitemewe, igihagararo cyumutekano, no gufungura.

Witondere

  • Gutangiza amatangazo arashobora gusumbya ituze mubikorwa nyabyo byakazi.
  • Ibiciro bya API cyangwa guhindura politiki birashobora guhagarika ibitekerezo ijoro ryose.
  • Abashoramari bonyine bishingira byongera gufunga no kwimuka.

Intambwe ikurikira

  1. Suzuma abatanga serivisi ukoresheje imirimo yawe bwite na datasets.
  2. Ongera usuzume ubuzima bwite, umutekano, namategeko mbere yo kwishyira hamwe.
  3. Komeza gahunda yo gusubira inyuma kurugero cyangwa abacuruzi.
  4. Kurikirana inyandiko zisohora kugirango impinduka zumuhanda ntizitangaje amakipe.

Komeza Ubushakashatsi

Ibaruwa y'amakuru y'ubuntu

Ibuka amakuru ya buri munsi ya AI

Inkuru eshatu zizewe za AI buri gitondo cy'iminsi y'akazi, zanditse mu rurimi rworoshye. Ubuntu iteka ryose, nta kwamamaza.

Imeri imwe buri munsi y'akazi. Kwiyimura mu buryo bumwe. Ntitwigera tugurisha cyangwa ngo dusangire aderesi yawe.

Isuzume

Take the BigScience and the BLOOM Model quiz

Ibisubizo ako kanya kuri buri kibazo, n'icyemezo gishobora gusangirwa gifite ID yagenzurwa umaze gutsinda isomo.

Tangira ikibazo

Fasha uburezi bwa AI bw'ubuntu. AI Understanding ni umuryango utegamiye kuri leta wa 501(c)(3) — nta kwamamaza, nta kwishyura, iteka ryose. Tanga impano

Ibibazo bikunze kubazwa

What is BigScience and the BLOOM Model?

BLOOM is a 176-billion-parameter multilingual language model produced by the BigScience collaboration and released with its research documentation. Its ROOTS training corpus included natural and programming languages, making it a prominent open-access research model.

Niyihe ntego yibanze yo gutandukanya icyitegererezo cya BLOOM ugereranije nubunini buringaniye bwigihe cyayo?

BLOOM yagenewe kuba indimi nyinshi kandi yarekuwe kumugaragaro hamwe ninyandiko zuzuye, bitandukanye na moderi zifunze zingana.

Hafi ya bangahe ibipimo BLOOM ifite?

BLOOM nicyitegererezo cya miliyari 176-yimiterere, uyishyira kurwego rusa na GPT-3.

Indimi zingahe BLOOM yatojwe gukora?

BLOOM's ROOTS Training corpus ikubiyemo indimi karemano 46 wongeyeho indimi 13 zo gutangiza.

Nuwuhe muryango wahuje ubufatanye bwa BigScience?

Guhobera Isura yahuje BigScience, amahugurwa y'abashakashatsi barenga 1.000.

BLOOM yatojwe he?

BLOOM yatojwe kuri super super mudasobwa ya Jean Zay mu Bufaransa, yerekana ko compte rusange ishobora guhugura urugero rwimbibi.